Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �性
    -0.07
     BUG
    -0.07
    _detected
    -0.07
     pInfo
    -0.07
    ชน
    -0.07
    
    -0.06
     उसस
    -0.06
     Edu
    -0.06
    ़ो
    -0.06
     Але
    -0.06
    POSITIVE LOGITS
    uxt
    0.07
     down
    0.06
    MenuBar
    0.06
    シ
    0.06
     вещ
    0.06
     mechanism
    0.06
    isses
    0.06
     books
    0.06
    ieee
    0.06
     bursts
    0.06
    Act Density 0.004%

    No Known Activations